Rel-LLM combines a GNN encoder with a frozen LLM via soft prompts and masked attribute pretraining, reporting improved average performance on RelBench relational database tasks.
InInternational Conference on Artificial Intelligence and Statistics, pages 5549–5581
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Large Language Models are Good Relational Learners
Rel-LLM combines a GNN encoder with a frozen LLM via soft prompts and masked attribute pretraining, reporting improved average performance on RelBench relational database tasks.